Pre-tunneling exploration for rock mass classification is a common practice in tunneling projects. This study proposes a data-driven approach that allows for rock mass classification. Two machine learning (ML) classification models, namely random forest (RF) and extremely randomized tree (ERT), are employed to classify the rock mass conditions encountered in the Pahang-Selangor Raw Water Tunnel in Malaysia using tunnel boring machine (TBM) operating parameters. Due to imbalance of rock classes distribution, an oversampling technique was used to obtain a balanced training dataset for unbiased learning of the ML models. A five-fold cross-validation approach was used to tune the model hyperparameters and validation-set approach was used for the model evaluation. ERT achieved an overall accuracy of 95%, while RF achieved 94% accuracy, in rightly classifying rock mass conditions. The result shows that the proposed approach has the potential to identify and correctly classify ground conditions of a TBM, which allows for early problem detection and on-the-fly support system selection based on the identified ground condition. This study, which is part of an ongoing effort towards developing reliable models that could be incorporated into TBMs, shows the potential of data-driven approaches for on-the-fly classification of ground conditions ahead of a TBM and could allow for the early detection of potential construction problems.
Rock mass rating used for selection of tunnel support type is a critical issue in tunneling. The wrong choice of tunnel support could lead to rock collapse and trapping of drilling rig. This study examines a novelty for the integration of drilling speed with rock properties to predict basic Rock Mass Rating (RMR) using Adaptive Neuro-Fuzzy Inference System (ANFIS). A database of 127 training and 32 testing datasets collected from NATM-3 of the tunnel was constructed. The input parameters are the Uniaxial Compressive Strength (UCS), Rock Quality Designation (RQD), Discontinuity Spacing (DS), groundwater (GW) and Drilling Speed (DSPEED), and the basic RMR as output parameter. Subtractive clustering method was used to generate the fuzzy Inference System and trained by the hybrid learning process in MATLAB R2018A software. Root mean squared error (RMSE) and Coefficient of determination (R2) were used to assess the performance of the developed model. The performance indices; R2 and RMSE of 0.892 and 2.576 respectively for the training and 0.846 and 2.316 for the testing model respectively were obtained. The results show that probe drilling speed and rock properties can be effectively integrated using ANFIS to predict basic rock mass rating in a tunnel.